{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T09:04:46Z","timestamp":1725959086376},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2148178"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","award":["FA9453-18-2-0022"],"id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006234","name":"Sandia National Laboratories","doi-asserted-by":"publisher","award":["DE-NA0003525"],"id":[{"id":"10.13039\/100006234","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3298601","type":"journal-article","created":{"date-parts":[[2023,7,25]],"date-time":"2023-07-25T17:38:13Z","timestamp":1690306693000},"page":"78192-78206","source":"Crossref","is-referenced-by-count":5,"title":["Multi-Agent Partial Observable Safe Reinforcement Learning for Counter Uncrewed Aerial Systems"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"http:\/\/orcid.org\/0009-0008-2024-3268","authenticated-orcid":false,"given":"Jean-Elie","family":"Pierre","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of New Mexico, Albuquerque, NM, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6954-7018","authenticated-orcid":false,"given":"Xiang","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of New Mexico, Albuquerque, NM, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5574-7246","authenticated-orcid":false,"given":"Rafael","family":"Fierro","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of New Mexico, Albuquerque, NM, USA"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Safe deep reinforcement learning for multi-agent systems with continuous action spaces","author":"sheebaelhamd","year":"2021","journal-title":"arXiv 2108 03952"},{"key":"ref35","article-title":"The before, during, and after of multi-robot deadlock","author":"grover","year":"2016","journal-title":"Int J Robot Res"},{"key":"ref12","article-title":"Safe exploration in continuous action spaces","author":"dalal","year":"2018","journal-title":"arXiv 1801 08757"},{"key":"ref34","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2444131"},{"key":"ref37","year":"2023","journal-title":"QP Solvers for Python"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812259"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10001678"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3264463"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"ref33","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","author":"yu","year":"2021","journal-title":"arXiv 2103 01955"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WOCC58016.2023.10139511"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3233004"},{"key":"ref17","article-title":"Multi-agent constrained policy optimisation","author":"gu","year":"2021","journal-title":"arXiv 2110 02793"},{"key":"ref16","first-page":"1","article-title":"A Lyapunov-based approach to safe reinforcement learning","volume":"31","author":"chow","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"3053","article-title":"RLLib: Abstractions for distributed reinforcement learning","author":"liang","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3000748"},{"key":"ref18","article-title":"Feasible actor-critic: Constrained reinforcement learning for ensuring statewise safety","author":"ma","year":"2021","journal-title":"arXiv 2105 10682"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR56537.2022.10018733"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/6979.898228"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461234"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-020-09945-6"},{"key":"ref20","article-title":"Learning safe multi-agent control with decentralized neural barrier certificates","author":"qin","year":"2021","journal-title":"arXiv 2101 05436"},{"key":"ref22","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"h\u00fcttenrauch","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref21","article-title":"Collision avoidance in pedestrian-rich environments with deep reinforcement learning","author":"everett","year":"2019","journal-title":"arXiv 1910 11689"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968560"},{"key":"ref27","first-page":"1","article-title":"Multi-agent deep reinforcement learning for countering uncrewed aerial systems","author":"pierre","year":"2022","journal-title":"Proc 16th Int Symp Distrib Auto Robotic Syst"},{"key":"ref29","article-title":"A review of cooperative multi-agent deep reinforcement learning","author":"oroojlooyjadid","year":"2019","journal-title":"arXiv 1908 03963"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068952"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/drones6070166"},{"key":"ref9","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc\u00eda","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/s20123537"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps56602.2022.10008619"},{"key":"ref6","first-page":"1","article-title":"Deep sets","volume":"30","author":"zaheer","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3245412"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/10005208\/10193774-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10193774.pdf?arnumber=10193774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:59:05Z","timestamp":1692640745000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10193774\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3298601","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}